Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4920 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9095. Min Range: -0.9095

Max Act: 0.9095. Min Act: -0.0000

Data Index: 754213 (C4 (Web Text))

Max Activating Token Index: 74

Text #1

Max Range: 0.9095. Min Range: -0.9095

Max Act: 0.8876. Min Act: -0.0000

Data Index: 666622 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 0.9095. Min Range: -0.9095

Max Act: 0.8815. Min Act: -0.0000

Data Index: 896686 (C4 (Web Text))

Max Activating Token Index: 72

Text #3

Max Range: 0.9095. Min Range: -0.9095

Max Act: 0.8478. Min Act: -0.0000

Data Index: 785734 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 0.9095. Min Range: -0.9095

Max Act: 0.8974. Min Act: -0.0000

Data Index: 801061 (C4 (Web Text))

Max Activating Token Index: 61

Text #5

Max Range: 0.9095. Min Range: -0.9095

Max Act: 0.8128. Min Act: -0.0000

Data Index: 70696 (C4 (Web Text))

Max Activating Token Index: 692

Text #6

Max Range: 0.9095. Min Range: -0.9095

Max Act: 0.8078. Min Act: -0.0000

Data Index: 15915 (C4 (Web Text))

Max Activating Token Index: 327

Text #7

Max Range: 0.9095. Min Range: -0.9095

Max Act: 0.8230. Min Act: -0.0000

Data Index: 1328531 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 0.9095. Min Range: -0.9095

Max Act: 0.7948. Min Act: -0.0000

Data Index: 1333122 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 0.9095. Min Range: -0.9095

Max Act: 0.8436. Min Act: -0.0000

Data Index: 640208 (C4 (Web Text))

Max Activating Token Index: 78

Text #10

Max Range: 0.9095. Min Range: -0.9095

Max Act: 0.7814. Min Act: -0.0000

Data Index: 670236 (C4 (Web Text))

Max Activating Token Index: 426

Text #11

Max Range: 0.9095. Min Range: -0.9095

Max Act: 0.8331. Min Act: -0.0000

Data Index: 999855 (C4 (Web Text))

Max Activating Token Index: 227

Text #12

Max Range: 0.9095. Min Range: -0.9095

Max Act: 0.8191. Min Act: -0.0000

Data Index: 148477 (C4 (Web Text))

Max Activating Token Index: 148

Text #13

Max Range: 0.9095. Min Range: -0.9095

Max Act: 0.8322. Min Act: -0.0000

Data Index: 382238 (C4 (Web Text))

Max Activating Token Index: 140

Text #14

Max Range: 0.9095. Min Range: -0.9095

Max Act: 0.7890. Min Act: -0.0000

Data Index: 1272928 (C4 (Web Text))

Max Activating Token Index: 60

Text #15

Max Range: 0.9095. Min Range: -0.9095

Max Act: 0.7499. Min Act: -0.0000

Data Index: 739553 (C4 (Web Text))

Max Activating Token Index: 967

Text #16

Max Range: 0.9095. Min Range: -0.9095

Max Act: 0.7248. Min Act: -0.0000

Data Index: 748110 (C4 (Web Text))

Max Activating Token Index: 1014

Text #17

Max Range: 0.9095. Min Range: -0.9095

Max Act: 0.8165. Min Act: -0.0000

Data Index: 501224 (C4 (Web Text))

Max Activating Token Index: 88

Text #18

Max Range: 0.9095. Min Range: -0.9095

Max Act: 0.7319. Min Act: -0.0000

Data Index: 1310453 (C4 (Web Text))

Max Activating Token Index: 155

Text #19

Max Range: 0.9095. Min Range: -0.9095

Max Act: 0.7792. Min Act: -0.0000

Data Index: 1319415 (C4 (Web Text))

Max Activating Token Index: 303